An AI-based Framework for Olive Disease Identification Using SqueezeNet, Artificial Neural Networks, and Support Vector Machines

Plant diseases pose a hazard to world food security. According to data from the Jordanian Department of Statistics, the olive crop was Jordan's greatest agricultural crop in terms of planted area and quantity produced in 2022. This study intends to use deep learning and machine learning approaches to identify olive crop illnesses. Image data was acquired from several sources and integrated into a single dataset. The data was split among 70% training and 30% testing. Deep learning SqueezeNet methods were used to extract features. Data training was conducted using both Artificial Neural Networks and Support Vector Machines models. In terms of accuracy, the Artificial Neural Network provided 92.9%, surpassing the Support Vector Machines model score of 85.5%.